alexeykudinkin commented on code in PR #7528:
URL: https://github.com/apache/hudi/pull/7528#discussion_r1067595140
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/BaseFileOnlyRelation.scala:
##########
@@ -106,18 +112,16 @@ class BaseFileOnlyRelation(sqlContext: SQLContext,
}
protected def collectFileSplits(partitionFilters: Seq[Expression],
dataFilters: Seq[Expression]): Seq[HoodieBaseFileSplit] = {
- val partitions = listLatestBaseFiles(globPaths, partitionFilters,
dataFilters)
- val fileSplits = partitions.values.toSeq
- .flatMap { files =>
- files.flatMap { file =>
- // TODO fix, currently assuming parquet as underlying format
- HoodieDataSourceHelper.splitFiles(
- sparkSession = sparkSession,
- file = file,
- partitionValues = getPartitionColumnsAsInternalRow(file)
- )
- }
- }
+ val fileSlices = listLatestFileSlices(globPaths, partitionFilters,
dataFilters)
Review Comment:
We only using the base-file from the file-slice there's no functional
change.
Were you refering to something else?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
